Big data application for analysis of flight test data

The analysis of huge data, represent a big interest, obtained from thousands of sensors, flight test and bench test data. Manual analysis of these is not possible. Data is read from the history database, focusing on not to miss interesting information for Health Monitoring Management of flight. This paper developing a workflow using big data techniques in determining the flight test data to be used for flight health monitoring system which could increase manufacturing, maintenance, operational efficiency, mission performance, and safety enhancements of present and future aerospace systems. As transient can be use to solve the problem, the Artificial Neural Networks would be used to identify and classify the transient patterns. This work proposes to develop a methodology for the Flight Health Monitoring Management. The proposed methodology trains and tests the Artificial Neural Network by using huge number of flight test data. The measurements of each new record are to be automatically classified by the developed Artificial Neural Network. By storing all the collected transient patterns in the distributed database (Hadoop), we can predict the future aircraft behavior of the components and can prevent events before happening, leading to good maintenance and health monitoring of the aerospace components.